cahya/last-sts

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Language: en

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("cahya/last-sts")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man plays the guitar.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

• Datasets: sts-dev and sts-test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-dev	sts-test
pearson_cosine	0.7982	0.7554
spearman_cosine	0.813	0.7644

Training Details

Training Dataset

Unnamed Dataset

• Size: 353,831 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 5 tokens mean: 38.53 tokens max: 151 tokens	min: 5 tokens mean: 38.78 tokens max: 145 tokens	min: 0.0 mean: 0.91 max: 1.0

• Samples:

  sentence1	sentence2	score
  A long-term researcher into diabetes, he achieved significant notability with his 1988 Banting Lecture (organized annually by the American Diabetes Association in memory of Frederick Banting).	A renowned expert on diabetes, he gained widespread acclaim for his 1988 Banting Lecture, which is presented annually by the American Diabetes Association to commemorate Frederick Banting.	0.926345705986023
  investigators claim the british company was a cia cover.	russian investigators stated that the british company was a cia cover.	0.88
  Albert Weber (21 November 1888, in Berlin – 17 September 1940) was a German amateur football (soccer) player who competed in the 1912 Summer Olympics.	Albert Weber (21 November 1888, in Berlin – 17 September 1940) was a German amateur footballer who participated in the 1912 Summer Olympics.	0.904914379119873

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

stsb

• Dataset: stsb at ab7a5ac
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 5 tokens mean: 15.44 tokens max: 44 tokens	min: 6 tokens mean: 15.43 tokens max: 58 tokens	min: 0.0 mean: 0.42 max: 1.0

• Samples:

  sentence1	sentence2	score
  A man with a hard hat is dancing.	A man wearing a hard hat is dancing.	1.0
  A young child is riding a horse.	A child is riding a horse.	0.95
  A man is feeding a mouse to a snake.	The man is feeding a mouse to the snake.	1.0

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• num_train_epochs: 10
• warmup_ratio: 0.1
• bf16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: True
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	sts-dev_spearman_cosine	sts-test_spearman_cosine
0.0362	100	0.0019	0.1114	0.8115	-
0.0724	200	0.0021	0.0882	0.8177	-
0.1085	300	0.0015	0.0748	0.8125	-
0.1447	400	0.0012	0.0679	0.8086	-
0.1809	500	0.0012	0.0608	0.8069	-
0.2171	600	0.001	0.0596	0.7986	-
0.2533	700	0.0011	0.0547	0.7946	-
0.2894	800	0.0011	0.0492	0.7870	-
0.3256	900	0.0009	0.0522	0.7862	-
0.3618	1000	0.0008	0.0519	0.7880	-
0.3980	1100	0.0009	0.0529	0.7962	-
0.4342	1200	0.0008	0.0469	0.7954	-
0.4703	1300	0.0009	0.0506	0.7928	-
0.5065	1400	0.0009	0.0466	0.7873	-
0.5427	1500	0.001	0.0495	0.7999	-
0.5789	1600	0.0008	0.0506	0.7861	-
0.6151	1700	0.0008	0.0522	0.7873	-
0.6512	1800	0.0009	0.0582	0.7843	-
0.6874	1900	0.0009	0.0585	0.7888	-
0.7236	2000	0.001	0.0508	0.8040	-
0.7598	2100	0.001	0.0483	0.8018	-
0.7959	2200	0.0008	0.0520	0.7841	-
0.8321	2300	0.0009	0.0519	0.7896	-
0.8683	2400	0.001	0.0514	0.7906	-
0.9045	2500	0.0009	0.0521	0.7946	-
0.9407	2600	0.0009	0.0496	0.7920	-
0.9768	2700	0.001	0.0566	0.7956	-
1.0130	2800	0.0009	0.0511	0.8044	-
1.0492	2900	0.0009	0.0622	0.8197	-
1.0854	3000	0.001	0.0504	0.8113	-
1.1216	3100	0.001	0.0550	0.8005	-
1.1577	3200	0.001	0.0549	0.7821	-
1.1939	3300	0.0009	0.0578	0.7758	-
1.2301	3400	0.0009	0.0543	0.7860	-
1.2663	3500	0.0008	0.0575	0.7891	-
1.3025	3600	0.0009	0.0567	0.7995	-
1.3386	3700	0.001	0.0488	0.7985	-
1.3748	3800	0.0009	0.0514	0.7789	-
1.4110	3900	0.001	0.0584	0.7765	-
1.4472	4000	0.001	0.0554	0.7888	-
1.4834	4100	0.001	0.0659	0.7959	-
1.5195	4200	0.0009	0.0511	0.7816	-
1.5557	4300	0.0009	0.0555	0.7826	-
1.5919	4400	0.001	0.0525	0.7944	-
1.6281	4500	0.0009	0.0553	0.7941	-
1.6643	4600	0.001	0.0588	0.7984	-
1.7004	4700	0.001	0.0579	0.8004	-
1.7366	4800	0.0009	0.0540	0.7916	-
1.7728	4900	0.0009	0.0557	0.7963	-
1.8090	5000	0.0008	0.0536	0.8044	-
1.8452	5100	0.0009	0.0541	0.7870	-
1.8813	5200	0.0009	0.0594	0.7989	-
1.9175	5300	0.001	0.0558	0.8000	-
1.9537	5400	0.0009	0.0538	0.7905	-
1.9899	5500	0.0008	0.0555	0.7944	-
2.0260	5600	0.0009	0.0557	0.8127	-
2.0622	5700	0.0007	0.0542	0.8146	-
2.0984	5800	0.0008	0.0517	0.7990	-
2.1346	5900	0.0009	0.0500	0.8051	-
2.1708	6000	0.0009	0.0521	0.8019	-
2.2069	6100	0.0009	0.0511	0.8101	-
2.2431	6200	0.0008	0.0578	0.8087	-
2.2793	6300	0.0008	0.0585	0.8012	-
2.3155	6400	0.0008	0.0566	0.8083	-
2.3517	6500	0.0007	0.0535	0.8036	-
2.3878	6600	0.0008	0.0531	0.7988	-
2.4240	6700	0.0007	0.0574	0.8102	-
2.4602	6800	0.0007	0.0566	0.7944	-
2.4964	6900	0.0008	0.0528	0.8058	-
2.5326	7000	0.0007	0.0528	0.8056	-
2.5687	7100	0.0007	0.0506	0.8002	-
2.6049	7200	0.0007	0.0526	0.8038	-
2.6411	7300	0.0007	0.0554	0.8054	-
2.6773	7400	0.0007	0.0505	0.7928	-
2.7135	7500	0.0007	0.0505	0.8070	-
2.7496	7600	0.0007	0.0535	0.7977	-
2.7858	7700	0.0007	0.0536	0.8019	-
2.8220	7800	0.0006	0.0546	0.7989	-
2.8582	7900	0.0007	0.0543	0.8042	-
2.8944	8000	0.0007	0.0542	0.8105	-
2.9305	8100	0.0007	0.0541	0.8053	-
2.9667	8200	0.0007	0.0545	0.8135	-
3.0029	8300	0.0007	0.0598	0.8201	-
3.0391	8400	0.0008	0.0558	0.8050	-
3.0753	8500	0.0007	0.0510	0.7965	-
3.1114	8600	0.0006	0.0564	0.8042	-
3.1476	8700	0.0006	0.0559	0.7932	-
3.1838	8800	0.0006	0.0529	0.8028	-
3.2200	8900	0.0006	0.0542	0.8142	-
3.2562	9000	0.0006	0.0532	0.8055	-
3.2923	9100	0.0006	0.0506	0.7930	-
3.3285	9200	0.0007	0.0542	0.7927	-
3.3647	9300	0.0006	0.0523	0.8033	-
3.4009	9400	0.0006	0.0530	0.8079	-
3.4370	9500	0.0006	0.0544	0.7977	-
3.4732	9600	0.0005	0.0515	0.8019	-
3.5094	9700	0.0006	0.0481	0.8037	-
3.5456	9800	0.0005	0.0557	0.8007	-
3.5818	9900	0.0006	0.0495	0.8087	-
3.6179	10000	0.0006	0.0555	0.7991	-
3.6541	10100	0.0005	0.0560	0.7973	-
3.6903	10200	0.0007	0.0581	0.7945	-
3.7265	10300	0.0006	0.0546	0.8098	-
3.7627	10400	0.0006	0.0539	0.8074	-
3.7988	10500	0.0005	0.0501	0.8051	-
3.8350	10600	0.0005	0.0531	0.8032	-
3.8712	10700	0.0005	0.0502	0.8077	-
3.9074	10800	0.0006	0.0537	0.8131	-
3.9436	10900	0.0005	0.0510	0.8115	-
3.9797	11000	0.0006	0.0525	0.8173	-
4.0159	11100	0.0005	0.0513	0.8106	-
4.0521	11200	0.0006	0.0594	0.8061	-
4.0883	11300	0.0005	0.0514	0.8150	-
4.1245	11400	0.0005	0.0537	0.8168	-
4.1606	11500	0.0005	0.0571	0.8176	-
4.1968	11600	0.0005	0.0546	0.8159	-
4.2330	11700	0.0005	0.0496	0.8115	-
4.2692	11800	0.0005	0.0526	0.8072	-
4.3054	11900	0.0005	0.0512	0.8081	-
4.3415	12000	0.0005	0.0517	0.8025	-
4.3777	12100	0.0005	0.0533	0.8128	-
4.4139	12200	0.0005	0.0501	0.8121	-
4.4501	12300	0.0005	0.0507	0.8079	-
4.4863	12400	0.0005	0.0501	0.8070	-
4.5224	12500	0.0004	0.0537	0.8019	-
4.5586	12600	0.0004	0.0541	0.8005	-
4.5948	12700	0.0005	0.0525	0.8117	-
4.6310	12800	0.0004	0.0523	0.8070	-
4.6671	12900	0.0005	0.0526	0.8099	-
4.7033	13000	0.0004	0.0518	0.8166	-
4.7395	13100	0.0004	0.0547	0.8129	-
4.7757	13200	0.0005	0.0523	0.8130	-
4.8119	13300	0.0004	0.0504	0.8129	-
4.8480	13400	0.0005	0.0539	0.8113	-
4.8842	13500	0.0004	0.0523	0.8169	-
4.9204	13600	0.0005	0.0521	0.8164	-
4.9566	13700	0.0004	0.0575	0.8115	-
4.9928	13800	0.0004	0.0538	0.8186	-
5.0289	13900	0.0004	0.0530	0.8095	-
5.0651	14000	0.0003	0.0537	0.8162	-
5.1013	14100	0.0004	0.0560	0.8112	-
5.1375	14200	0.0004	0.0528	0.8125	-
5.1737	14300	0.0004	0.0533	0.8137	-
5.2098	14400	0.0003	0.0537	0.8198	-
5.2460	14500	0.0004	0.0530	0.8102	-
5.2822	14600	0.0004	0.0562	0.8099	-
5.3184	14700	0.0004	0.0522	0.8084	-
5.3546	14800	0.0004	0.0515	0.8128	-
5.3907	14900	0.0004	0.0555	0.8107	-
5.4269	15000	0.0004	0.0533	0.8113	-
5.4631	15100	0.0003	0.0538	0.8135	-
5.4993	15200	0.0004	0.0552	0.8139	-
5.5355	15300	0.0003	0.0513	0.8102	-
5.5716	15400	0.0004	0.0542	0.8108	-
5.6078	15500	0.0003	0.0541	0.8041	-
5.6440	15600	0.0004	0.0512	0.8074	-
5.6802	15700	0.0003	0.0553	0.8100	-
5.7164	15800	0.0003	0.0539	0.8088	-
5.7525	15900	0.0004	0.0527	0.8094	-
5.7887	16000	0.0004	0.0524	0.8080	-
5.8249	16100	0.0003	0.0525	0.8112	-
5.8611	16200	0.0003	0.0537	0.8109	-
5.8973	16300	0.0003	0.0539	0.8129	-
5.9334	16400	0.0003	0.0543	0.8052	-
5.9696	16500	0.0003	0.0544	0.8093	-
6.0058	16600	0.0004	0.0532	0.8109	-
6.0420	16700	0.0002	0.0558	0.8108	-
6.0781	16800	0.0002	0.0529	0.8089	-
6.1143	16900	0.0003	0.0539	0.8074	-
6.1505	17000	0.0003	0.0534	0.8118	-
6.1867	17100	0.0003	0.0539	0.8048	-
6.2229	17200	0.0003	0.0537	0.8049	-
6.2590	17300	0.0003	0.0553	0.8102	-
6.2952	17400	0.0002	0.0533	0.8053	-
6.3314	17500	0.0003	0.0550	0.8071	-
6.3676	17600	0.0002	0.0530	0.8128	-
6.4038	17700	0.0003	0.0547	0.8159	-
6.4399	17800	0.0002	0.0539	0.8120	-
6.4761	17900	0.0003	0.0540	0.8107	-
6.5123	18000	0.0003	0.0535	0.8069	-
6.5485	18100	0.0003	0.0541	0.8129	-
6.5847	18200	0.0003	0.0522	0.8132	-
6.6208	18300	0.0002	0.0539	0.8135	-
6.6570	18400	0.0002	0.0542	0.8142	-
6.6932	18500	0.0003	0.0529	0.8101	-
6.7294	18600	0.0003	0.0533	0.8073	-
6.7656	18700	0.0003	0.0525	0.8095	-
6.8017	18800	0.0003	0.0534	0.8089	-
6.8379	18900	0.0002	0.0519	0.8134	-
6.8741	19000	0.0002	0.0536	0.8141	-
6.9103	19100	0.0002	0.0535	0.8115	-
6.9465	19200	0.0002	0.0519	0.8107	-
6.9826	19300	0.0002	0.0546	0.8093	-
7.0188	19400	0.0002	0.0532	0.8112	-
7.0550	19500	0.0002	0.0526	0.8145	-
7.0912	19600	0.0002	0.0529	0.8111	-
7.1274	19700	0.0002	0.0540	0.8090	-
7.1635	19800	0.0002	0.0525	0.8116	-
7.1997	19900	0.0002	0.0534	0.8115	-
7.2359	20000	0.0002	0.0526	0.8123	-
7.2721	20100	0.0002	0.0524	0.8143	-
7.3082	20200	0.0002	0.0526	0.8059	-
7.3444	20300	0.0002	0.0535	0.8091	-
7.3806	20400	0.0002	0.0532	0.8094	-
7.4168	20500	0.0002	0.0529	0.8108	-
7.4530	20600	0.0002	0.0542	0.8108	-
7.4891	20700	0.0002	0.0525	0.8102	-
7.5253	20800	0.0002	0.0541	0.8106	-
7.5615	20900	0.0002	0.0538	0.8095	-
7.5977	21000	0.0003	0.0523	0.8136	-
7.6339	21100	0.0002	0.0544	0.8108	-
7.6700	21200	0.0002	0.0525	0.8090	-
7.7062	21300	0.0002	0.0528	0.8108	-
7.7424	21400	0.0002	0.0531	0.8115	-
7.7786	21500	0.0002	0.0541	0.8107	-
7.8148	21600	0.0001	0.0525	0.8117	-
7.8509	21700	0.0002	0.0534	0.8115	-
7.8871	21800	0.0002	0.0541	0.8105	-
7.9233	21900	0.0002	0.0538	0.8094	-
7.9595	22000	0.0002	0.0530	0.8106	-
7.9957	22100	0.0002	0.0527	0.8104	-
8.0318	22200	0.0001	0.0534	0.8098	-
8.0680	22300	0.0002	0.0537	0.8090	-
8.1042	22400	0.0001	0.0533	0.8103	-
8.1404	22500	0.0002	0.0528	0.8099	-
8.1766	22600	0.0001	0.0531	0.8106	-
8.2127	22700	0.0001	0.0534	0.8116	-
8.2489	22800	0.0001	0.0538	0.8102	-
8.2851	22900	0.0001	0.0530	0.8108	-
8.3213	23000	0.0002	0.0529	0.8112	-
8.3575	23100	0.0001	0.0533	0.8099	-
8.3936	23200	0.0001	0.0534	0.8107	-
8.4298	23300	0.0002	0.0535	0.8110	-
8.4660	23400	0.0001	0.0543	0.8108	-
8.5022	23500	0.0001	0.0530	0.8119	-
8.5384	23600	0.0001	0.0530	0.8132	-
8.5745	23700	0.0001	0.0531	0.8128	-
8.6107	23800	0.0002	0.0532	0.8119	-
8.6469	23900	0.0002	0.0531	0.8120	-
8.6831	24000	0.0001	0.0531	0.8121	-
8.7192	24100	0.0001	0.0525	0.8134	-
8.7554	24200	0.0002	0.0524	0.8133	-
8.7916	24300	0.0001	0.0535	0.8141	-
8.8278	24400	0.0002	0.0529	0.8118	-
8.8640	24500	0.0001	0.0529	0.8115	-
8.9001	24600	0.0001	0.0528	0.8127	-
8.9363	24700	0.0002	0.0527	0.8111	-
8.9725	24800	0.0001	0.0536	0.8114	-
9.0087	24900	0.0001	0.0531	0.8124	-
9.0449	25000	0.0001	0.0532	0.8123	-
9.0810	25100	0.0001	0.0534	0.8130	-
9.1172	25200	0.0001	0.0533	0.8121	-
9.1534	25300	0.0002	0.0534	0.8119	-
9.1896	25400	0.0001	0.0532	0.8118	-
9.2258	25500	0.0001	0.0532	0.8112	-
9.2619	25600	0.0001	0.0532	0.8121	-
9.2981	25700	0.0002	0.0537	0.8120	-
9.3343	25800	0.0001	0.0535	0.8127	-
9.3705	25900	0.0001	0.0529	0.8133	-
9.4067	26000	0.0001	0.0529	0.8138	-
9.4428	26100	0.0001	0.0534	0.8131	-
9.4790	26200	0.0001	0.0529	0.8137	-
9.5152	26300	0.0002	0.0529	0.8135	-
9.5514	26400	0.0001	0.0528	0.8129	-
9.5876	26500	0.0001	0.0530	0.8124	-
9.6237	26600	0.0001	0.0529	0.8132	-
9.6599	26700	0.0001	0.0530	0.8128	-
9.6961	26800	0.0001	0.0530	0.8132	-
9.7323	26900	0.0001	0.0529	0.8129	-
9.7685	27000	0.0002	0.0528	0.8131	-
9.8046	27100	0.0001	0.0529	0.8131	-
9.8408	27200	0.0002	0.0531	0.8128	-
9.8770	27300	0.0001	0.0532	0.8130	-
9.9132	27400	0.0001	0.0531	0.8129	-
9.9493	27500	0.0001	0.0531	0.8129	-
9.9855	27600	0.0001	0.0531	0.8130	-
-1	-1	-	-	-	0.7644

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 3.4.1
• Transformers: 4.49.0
• PyTorch: 2.5.1+cu124
• Accelerate: 0.34.2
• Datasets: 2.19.2
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}